Introduction

Open Source MIT License

awa (Agent Workflow for AIs) is an open-source CLI tool that generates AI coding agent configuration files from templates with feature flags. It solves the problem of AI agent configuration drift and lack of traceability in AI-assisted development.

The Problem

Developing with AI agents requires process. Configuration files that define this process get copy-pasted between projects, then diverge. Requirements live in one place, implementation in another, tests in a third — nothing connects them. They diverge too.

Without structure, work drifts and nobody — including the AI — can trace what happened or why.

The Solution

awa generates agent configuration files from templates with feature flags. The generated output includes a spec-driven development workflow with full traceability:

ARCHITECTURE → FEAT → REQUIREMENTS → DESIGN → TASKS → CODE & TESTS → DOCUMENTATION

Every artifact traces back to its origin through explicit markers (@awa-impl, @awa-test, @awa-component). Any line of code traces back to the requirement that motivated it. Any requirement traces forward to the tests that verify it.

Key Features

Workflow & Traceability

• Structured workflow from architecture through features, requirements, design, tasks, code, tests, and docs
• Requirements written in EARS format (INCOSE) — structured, testable, unambiguous
• Every requirement has an ID; every line of code links back to it via @awa-impl and @awa-test markers
• Spec artifacts (requirements, designs, tasks, plans, rules) all live in .awa/

CLI & Template Engine

• Eta templates with conditionals, loops, and partials
• Feature flags and presets to turn content on/off per project
• awa diff shows exactly what changed before you commit
• Pull templates from GitHub, GitLab, Bitbucket, or use a local path
• Optional .awa.toml config, or just use CLI flags

Philosophy

awa was written by awa — AI-assisted development using its own workflows. The workflows themselves are designed and crafted by a human who uses Copilot. If something is wrong, let’s fix it together.

awa is agent-agnostic: it generates configuration for GitHub Copilot, Claude, Cursor, Windsurf, and more — all from a single template set. It makes no assumptions about which AI tool you use or how you use it.

Next Steps

• Quick Start — install awa and generate your first configuration in minutes
• Workflow Guide — understand the full workflow and traceability chain
• CLI Reference — all commands, options, and configuration